INDEX

Explanations

numerical data, particularly in structured formats

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

GEBURTSDATUM

-1.00

StoryboardSegue

-0.97

ⓧ

-0.95

parsedMessage

-0.88

 resourceCulture

-0.87

BeginInit

-0.82

PerformLayout

-0.81

 beginnetje

-0.77

Personendaten

-0.76

SequentialGroup

-0.76

POSITIVE LOGITS

0.58

0.54

0.53

 tale

0.52

0.51

subsubsection

0.51

0.50

0.47

Activations Density 0.957%

numerical data, particularly in structured formats

No Comments

No Known Activations